from pyspark.sql import SparkSession

spark = SparkSession.builder.appName("your_app_name").getOrCreate()
df = spark.read.parquet("s3://amazon-reviews-pds/parquet/product_category=Electronics/")
df.limit(5).toPandas()

from pyspark.sql import SparkSession
import pyspark.sql.functions as spark_functions
import pyspark_anonymizer

spark = SparkSession.builder.appName("your_app_name").getOrCreate()
df = spark.read.parquet("s3://amazon-reviews-pds/parquet/product_category=Electronics/")

dataframe_anonymizers = [
    {
        "method": "drop_column",
        "parameters": {
            "column_name": "marketplace"
        }
    },
    {
        "method": "replace",
        "parameters": {
            "column_name": "customer_id",
            "replace_to": "*"
        }
    },
    {
        "method": "replace_with_regex",
        "parameters": {
            "column_name": "review_id",
            "replace_from_regex": "R\d",
            "replace_to": "*"
        }
    },
    {
        "method": "sha256",
        "parameters": {
            "column_name": "product_id"
        }
    },
    {
        "method": "filter_row",
        "parameters": {
            "where": "product_parent != 738692522"
        }
    }
]

df_parsed = pyspark_anonymizer.Parser(df, dataframe_anonymizers, spark_functions).parse()
df_parsed.limit(5).toPandas()

from pyspark.sql import SparkSession
import pyspark.sql.functions as spark_functions
import pyspark_anonymizer
import boto3
from botocore.exceptions import ClientError as client_error

dynamo_table = "pyspark_anonymizer"
dataframe_name = "table_x"

dynamo_table = boto3.resource('dynamodb').Table(dynamo_table)
spark = SparkSession.builder.appName("your_app_name").getOrCreate()
df = spark.read.parquet("s3://amazon-reviews-pds/parquet/product_category=Electronics/")

df_parsed = pyspark_anonymizer.ParserFromDynamoDB(df, dataframe_name, dynamo_table, spark_functions, client_error).parse()

df_parsed.limit(5).toPandas()